Quantitative Evaluation of Flame Image Stability Based on Convolutional Autoencoder

WANG An; WEN Wubin; LIU Hongwen; HAN Zhezhe; XU Chuanlong

doi:10.19805/j.cnki.jcspe.2025.230781

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Quantitative Evaluation of Flame Image Stability Based on Convolutional Autoencoder

更新时间：2026-02-02

- Quantitative Evaluation of Flame Image Stability Based on Convolutional Autoencoder
- Chinese Journal of Power Engineering Vol. 45, Issue 3, Pages: 325-333(2025)
- 作者机构：
  
  1. 国能常州发电有限公司,江苏,常州,213033
  2. 国家能源集团江苏电力有限公司,江苏,南京,215433
  3. 南京工程学院信息与通信工程学院,江苏,南京,211167
  4. 东南大学能源与环境学院,江苏,南京,210096
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.230781
  CLC： X924.2;TP391.41
- Published Online：15 March 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
王安,温武斌,刘宏文,韩哲哲,许传龙. 基于卷积自编码的火焰图像稳定性定量评估动力工程学报, 2025, 45(3): 325-333 https://doi.

org/10.19805/j.cnki.jcspe.2025.230781
王安,温武斌,刘宏文,韩哲哲,许传龙. 基于卷积自编码的火焰图像稳定性定量评估动力工程学报, 2025, 45(3): 325-333 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.230781.

org/10.19805/j.cnki.jcspe.2025.230781 DOI：

摘要

提出了一种火焰图像稳定性定量评估方法

首先采用卷积自编码对火焰图像进行特征提取

然后利用定量评估指标予以特征分析。定量评估指标建立在图像特征的聚类分析和统计分析基础上

其数值区间为[0

1]。卷积自编码采用一种基于重建相似性的新损失函数

以提高训练效率。同时

在乙烯燃烧平台上开展试验研究

以验证火焰图像稳定性定量评估方法的有效性。结果表明:卷积自编码能够以无监督方式提取火焰图像特征

其性能明显优于传统特征学习方法;所建立的定量评估指标可以量化表征火焰图像稳定性

展现出极强的泛化能力。

Abstract

A quantitative evaluation method for flame image stability was proposed. First

convolutional autoencoder was used to extract features from flame images

and then quantitative evaluation index was employed for feature analysis. The quantitative evaluation index

with a numerical interval of [0

was established based on cluster analysis and statistical analysis of the image feature. The convolutional autoencoder adopted a novel loss function based on reconstruction similarity to improve training efficiency. The effectiveness of the quantitative evaluation method for flame image stability was verified through experiments on the ethylene combustion platform. Results show that the convolutional autoencoder can extract image features in an unsupervised manner

and its performance is obviously superior to traditional feature learning methods. In addition

the established quantitative evaluation index can quantitatively characterize the flame image stability

showing strong generalization ability.

关键词

Keywords

references

马达夫, 刘平元, 张守玉, 等. 超低负荷下运行氧量对切圆锅炉燃烧稳定性和NO x 排放特性的影响[J ] . 动力工程学报, 2023, 43(2): 174-184. MA Dafu, LIU Pingyuan, ZHANG Shouyu, et al. Effect of boiler operation oxygen on combustion stability and NO x emission characteristics of a tangentially fired boiler under ultra-low load[J ] . Journal of Chinese Society of Power Engineering, 2023, 43(2): 174-184.

张绪辉, 杨兴森, 辛刚, 等. 燃煤火电机组深度调峰运行试验[J]. 洁净煤技术, 2022, 28(4): 144-150. ZHANG Xuhui, YANG Xingsen, XIN Gang, et al. Experimental study on deep peak regulation operation of coal-fired thermal power unit[J]. Clean Coal Technology, 2022, 28(4): 144-150.

宋民航, 黄云, 黄骞, 等. 旋流煤粉燃烧器低负荷稳燃技术探讨[J]. 中国电机工程学报, 2021, 41(13): 4552-4565. SONG Minhang, HUANG Yun, HUANG Qian, et al. Discussion on low-load stable combustion technology of swirl pulverized-coal burner[J]. Proceedings of the CSEE, 2021, 41(13): 4552-4565.

马达夫, 张守玉, 何翔, 等. 煤粉锅炉超低负荷运行的技术问题和应对措施[J]. 动力工程学报, 2019, 39(10): 784-791, 803. MA Dafu, ZHANG Shouyu, HE Xiang, et al. Technical problems occurring in ultra-low load operation of pulverized coal-fired boilers and the solutions[J]. Journal of Chinese Society of Power Engineering, 2019, 39(10): 784-791, 803.

刘辉, 周科, 解冰, 等. 基于火焰温度场在线测量的燃煤锅炉深度调峰试验[J]. 热力发电, 2019, 48(8): 49-54. LIU Hui, ZHOU Ke, XIE Bing, et al. Experimental investigation on deep peak load regulation of coal-fired boiler based on on-line measurement of flame temperature field[J]. Thermal Power Generation, 2019, 48(8): 49-54.

韩哲哲. 基于数据驱动的火焰图像识别与燃烧诊断方法研究[D]. 南京: 东南大学, 2022.

ALIRAMEZANI M, KOCH C R, SHAHBAKHTI M. Modeling, diagnostics, optimization, and control of internal combustion engines via modern machine learning techniques: a review and future directions[J]. Progress in Energy and Combustion Science, 2022, 88: 100967.

MESSERLY R A, RAHIMI M J, ST JOHN P C, et al. Towards quantitative prediction of ignition-delay-time sensitivity on fuel-to-air equivalence ratio[J]. Combustion and Flame, 2020, 214: 103-115.

MARDANI A, LIAO Huchang, NILASHI M, et al. A multi-stage method to predict carbon dioxide emissions using dimensionality reduction, clustering, and machine learning techniques[J]. Journal of Cleaner Production, 2020, 275: 122942.

KATZER C, BABUL K, KLATT M, et al. Quantitative and qualitative relationship between swirl burner operating conditions and pulverized coal flame length[J]. Fuel Processing Technology, 2017, 156: 138-155.

ZHOU Yuchen, ZHANG Chi, HAN Xiao, et al. Monitoring combustion instabilities of stratified swirl flames by feature extractions of time-averaged flame images using deep learning method[J]. Aerospace Science and Technology, 2021, 109: 106443.

SUN Duo, LU Gang, ZHOU Hao, et al. Quantitative assessment of flame stability through image processing and spectral analysis[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(12): 3323-3333.

WANG Yu, YU Yuefeng, ZHU Xiaolei, et al. Pattern recognition for measuring the flame stability of gas-fired combustion based on the image processing technology[J]. Fuel, 2020, 270: 117486.

白卫东, 严建华, 池涌, 等. 基于图像技术和PCA方法的火焰监测研究[J]. 动力工程, 2004, 24(1): 87-90. BAI Weidong, YAN Jianhua, CHI Yong, et al. Research on flame monitoring based on image processing technology and PCA method[J]. Power Engineering, 2004, 24(1): 87-90.

CHEN Junghui, CHANG Y H, CHENG Yicheng, et al. Design of image-based control loops for industrial combustion processes[J]. Applied Energy, 2012, 94: 13-21.

CHEN Junghui, HSU T Y, CHEN C C, et al. Monitoring combustion systems using HMM probabilistic reasoning in dynamic flame images[J]. Applied Energy, 2010, 87(7): 2169-2179.

闾曾怡, 王高峰, 杨瑶, 等. 基于CNN-LSTM深度学习的燃烧不稳定性检测方法研究[J]. 燃烧科学与技术, 2022, 28(2): 119-125. L Zengyi, WANG Gaofeng, YANG Yao, et al. Combustion instability detection method based on CNN-LSTM deep learning[J]. Journal of Combustion Science and Technology, 2022, 28(2): 119-125.

何涛, 王思睿, 卫思霁, 等. 基于深度学习的贫燃熄火预测方法和实验研究[J]. 燃烧科学与技术, 2022, 28(3): 304-312. HE Tao, WANG Sirui, WEI Siji, et al. Prediction method and experimental research on lean burn blow-off based on deep learning[J]. Journal of Combustion Science and Technology, 2022, 28(3): 304-312.

WANG Zhenyu, SONG Chunfeng, CHEN Tao. Deep learning based monitoring of furnace combustion state and measurement of heat release rate[J]. Energy, 2017, 131: 106-112.

RONCANCIO R, EL GAMAL A, GORE J P. Turbulent flame image classification using convolutional neural networks[J]. Energy and AI, 2022, 10: 100193.

HAN Zhezhe, TANG Xiaoyu, HOSSAIN M M, et al. Assessment of flame stability through a convolutional denoising autoencoder and statistical analysis [J]. Combustion and Flame, 2023, 258: 113069.

蔡国源, 牛玉广, 刘雪菲, 等. 基于图像卷积变分自编码的电站锅炉燃烧稳定性评价方法[J]. 仪器仪表学报, 2022, 43(3): 211-220. CAI Guoyuan, NIU Yuguang, LIU Xuefei, et al. Combustion stability judgment of power plant boiler based on image convolutional variational auto-encoder[J]. Chinese Journal of Scientific Instrument, 2022, 43(3): 210-220.

王煜伟, 田宏伟, 秦永新, 等. 基于火焰图像和卷积稀疏自编码的燃烧工况监测[J]. 动力工程学报, 2020, 40(9): 713-719. WANG Yuwei, TIAN Hongwei, QIN Yongxin, et al. Combustion condition monitoring based on flame imaging and convolutional sparse auto encoder[J]. Journal of Chinese Society of Power Engineering, 2020, 40(9): 713-719.

MAJID S, ALENEZI F, MASOOD S, et al. Attention based CNN model for fire detection and localization in real-world images[J]. Expert Systems with Applications, 2022, 189: 116114.

SHI Shengxian, WANG Jianhua, DING Junfei, et al. Parametric study on light field volumetric particle image velocimetry[J]. Flow Measurement and Instrumentation, 2016, 49: 70-88.

张红亮. 氧化铝回转窑火焰图像识别、检索与聚类研究[D]. 长沙: 中南大学, 2008.

韩佳佳, 贾继德, 贾翔宇, 等. 基于幅值概率统计与SVM的柴油机失火故障诊断[J]. 军事交通学院学报, 2018, 20(2): 45-50. HAN Jiajia, JIA Jide, JIA Xiangyu, et al. Misfire fault diagnosis of diesel engine based on amplitude probability statistics and SVM[J]. Journal of Military Transportation University, 2018, 20(2): 45-50.

杨甫江, 郭志辉, 任立磊. 贫燃预混旋流火焰的燃烧不稳定性[J]. 燃烧科学与技术, 2014, 20(1): 51-57. YANG Fujiang, GUO Zhihui, REN Lilei. Combustion instability of lean premixed swirl flame[J]. Journal of Combustion Science and Technology, 2014, 20(1): 51-57.

KIM Joonsuk, CHUN K M, SONG Soonho, et al. Hydrogen effects on the combustion stability, performance and emissions of a turbo gasoline direct injection engine in various air/fuel ratios[J]. Applied Energy, 2018, 228: 1353-1361.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Main Steam Temperature Prediction for Waste Incinerator Based on IGRA and CNN-LSTM

Research of Li₄SiO₄ irradiation tritium production device

Synthesis of functional polymers by pre-radiation induced grafting of acrylaldehyde onto FEP film

Thermal safety analysis of aluminum matrix B₄C irradiation in-pile

Pulse radiolysis and laser flash photolysis study of balofloxacin

Related Author

WANG Yinsong

ZHANG Ju

Related Institution

Department of Automation, North China Electric Power University

Baoding Key Laboratory of State Detection and Optimization Regulation for Integrated Energy System

Hebei Technology Innovation Center of Simulation & Optimized Control for Power Generation

AI问答

⁰